Automatic fault classification for model-based process monitoring

Abstract

A computer implemented method, system and program product for automatic fault classification. A set of abnormal data can be automatically grouped based on sensor contribution to a prediction error. A principal component analysis (PCA) model of normal behavior can then be applied to a set of newly generated data, in response to automatically grouping the set of abnormal data based on the sensor contribution to the prediction error. Data points can then be identified, which are indicative of abnormal behavior. Such an identification step can occur in response to applying the principal component analysis mode of normal behavior to the set of newly generated data in order to cluster and classify the data points in order to automatically classify one or more faults thereof. The data points are automatically clustered, in order to identify a set of similar events, in response to identifying the data points indicative of abnormal behavior.

Description

TECHNICAL FIELD[0001]Embodiments are generally related to data-processing systems and methods. Embodiments are also related to automatic fault classification and principal component analysis (PCA).BACKGROUND[0002]Early event detection (EED) systems are designed to assist the operations team by providing early warnings of approaching process upsets. EED systems use multivariate statistics and pattern recognition algorithms to monitor continuous time-series data to provide early warning of operational shifts that may drive a system into a hazardous state. The core of an EED system is a set of state estimators that embed monitoring algorithms. These algorithms use time series process data to assess the health of the monitored process. Although numerous state estimators exist, such as Principal Component Analysis (PCA), that are able to detect abnormality, the challenge lies in the translation of their output into information that is meaningful to the process operator. Currently, EED sy...

AI Technical Summary

Benefits of technology

[0011]It is yet another aspect of the present invention to provide an improved data-processing method and system that can be used as a part of an abnormal situation management produ

Problems solved by technology

Although numerous state estimators exist, such as Principal Component Analysis (PCA), that are able to detect abnormality, the challenge lies in the translation of their output into information that is meaningful to the process operator.

While capable of detecting various anomalies, these applications are only able to localize some predefined failure conditions.

Unfortunately, this representation can potentially lead to poor clustering results.

This is because a process is usually measured by large number of sensors, while each fault is usually caused by only a small part of the process.

Therefore, if residuals

Images